feat: add model script, training recipe and pretrained weight of cmt_s #680
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
wcrzlh
force-pushed
the
cmt
branch
3 times, most recently
from
3c4214a
to
d9bdd27
Compare
geniuspatrick
requested changes
Jun 21, 2023
mindcv/models/cmt.py
Outdated
| to_2tuple = _ntuple(2) | ||
|
|
||
|
|
||
| class DropPath(nn.Cell): |
configs/cmt/README.md
Outdated
|
|
||
| ### Deployment | ||
|
|
||
| Please refer to the [deployment tutorial](https://github.com/mindspore-lab/mindcv/blob/main/tutorials/deployment.md) in MindCV. |
mindcv/models/cmt.py
Outdated
| nn.Conv2d(hidden_features, out_features, 1, 1, has_bias=True), | ||
| nn.BatchNorm2d(out_features), | ||
| ]) | ||
| self.drop = nn.Dropout(keep_prob=1-drop) |
mindcv/models/cmt.py
Outdated
|
|
||
|
|
||
| def swish(x): | ||
| return x * P.Sigmoid()(x) |
mindcv/models/cmt.py
Outdated
|
|
||
| def construct(self, x, H, W): | ||
| B, _, C = x.shape | ||
| x = ops.Transpose()(x, (0, 2, 1)).reshape(B, C, H, W) |
mindcv/models/cmt.py
Outdated
| self.patch_embed_d = PatchEmbed( | ||
| img_size=img_size // 16, patch_size=2, in_chans=embed_dims[2], embed_dim=embed_dims[3]) | ||
|
|
||
| self.relative_pos_a = P.Zeros()( |
wcrzlh
force-pushed
the
cmt
branch
2 times, most recently
from
b18be79
to
720e601
Compare
|
fixed |
geniuspatrick
requested changes
Jun 30, 2023
mindcv/models/cmt.py
Outdated
|
|
||
| class CMT(nn.Cell): | ||
| def __init__( | ||
| self, |
mindcv/models/cmt.py
Outdated
| self.patch_embed_d = PatchEmbed( | ||
| img_size=img_size // 16, patch_size=2, in_chans=embed_dims[2], embed_dim=embed_dims[3]) | ||
|
|
||
| self.relative_pos_a = ops.Zeros()( |
|
fixed |
SamitHuang
reviewed
Jul 6, 2023
| momentum: 0.9 | ||
| weight_decay: 0.05 | ||
| loss_scale_type: 'dynamic' | ||
| loss_scale: 16777216.0 |
There was a problem hiding this comment.
This is really large. How can you get this magic number?
There was a problem hiding this comment.
I use the initial loss scale(2**24) in mindspore.amp.DynamicLossScaleManager.
SamitHuang
approved these changes
Jul 8, 2023
geniuspatrick
approved these changes
Jul 10, 2023
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Thank you for your contribution to the MindCV repo.
Before submitting this PR, please make sure:
Motivation
The model script, training recipe and pertained weight of cmt_small is added.
Test Plan
Please refer to 'configs/cmt/README.md' for testing and reproducing.
Related Issues and PRs
(Is this PR part of a group of changes? Link the other relevant PRs and Issues here. Use https://help.github.com/en/articles/closing-issues-using-keywords for help on GitHub syntax)